oci: drop params automatically and add DEDICATED Support

litellm/llms/oci/chat/transformation.py

@@ -207,9 +207,9 @@ class OCIChatConfig(BaseConfig):
             alias = open_ai_to_oci_param_map.get(key)
 
             if alias is False:
-                if drop_params:
-                    continue
-
+                # Workaround for mypy issue
+                #if drop_params:
+                continue
                 raise Exception(f"param `{key}` is not supported on OCI")
 
             if alias is None:
@@ -450,12 +450,26 @@ class OCIChatConfig(BaseConfig):
                 "Cohere models are not yet supported in the litellm OCI chat completion endpoint. Use the Cohere API directly."
             )
         else:
-            data = OCICompletionPayload(
-                compartmentId=oci_compartment_id,
-                servingMode=OCIServingMode(
+            oci_serving_mode = optional_params.get("oci_serving_mode", "ON_DEMAND")
+            if oci_serving_mode not in ["ON_DEMAND", "DEDICATED"]:
+                raise Exception(
+                    "kwarg `oci_serving_mode` must be either 'ON_DEMAND' or 'DEDICATED'"
+                )
+
+            if oci_serving_mode == "DEDICATED":
+                servingMode = OCIServingMode(
+                    servingType="DEDICATED",
+                    endpointId=model,
+                )
+            else:
+                servingMode = OCIServingMode(
                     servingType="ON_DEMAND",
                     modelId=model,
-                ),
+                )
+
+            data = OCICompletionPayload(
+                compartmentId=oci_compartment_id,
+                servingMode=servingMode,
                 chatRequest=OCIChatRequestPayload(
                     apiFormat=vendor.value,
                     messages=adapt_messages_to_generic_oci_standard(messages),
@@ -601,6 +615,11 @@ class OCIChatConfig(BaseConfig):
         if "stream" in data:
             del data["stream"]
 
+        stops = data.get("chatRequest", {}).get("stop")
+        if stops and len(stops) > 8:
+            # mantém apenas os 8 primeiros
+            data["chatRequest"]["stop"] = stops[:8]
+
         if client is None or isinstance(client, HTTPHandler):
             client = get_async_httpx_client(llm_provider=LlmProviders.BYTEZ, params={})
 

litellm/types/llms/oci.py

@@ -100,8 +100,8 @@ class OCIServingMode(BaseModel):
     """Defines the serving mode and the model to be used."""
 
     servingType: str
-    modelId: str
-
+    endpointId: Optional[str] = None
+    modelId: Optional[str] = None
 
 class OCICompletionPayload(BaseModel):
     """Pydantic model for the complete OCI chat request body."""
@@ -129,7 +129,7 @@ class OCIPromptTokensDetails(BaseModel):
 
 class OCIResponseUsage(BaseModel):
     """Token usage in the OCI response."""
-    
+
     promptTokens: int
     completionTokens: int
     totalTokens: int